Preview. These maps are our reading of public sources and haven't been checked with the projects' maintainers yet.
OpenAPPA
Deterministic, flow-tracking guardrail (Agentic Permissions Policy Algebra): labels everything an agent reads by audience and trust and checks each tool call against it, returning remedies instead of bare denials.
openappa.com/Active
v0.37.0 released 2026-10-20; repo created 2026-08-18; 1.6k stars. (checked 2026-10-25)
In Agent guardrails
Where it stands apart
- What is the main thing it protects? outside systems and data (APIs, databases, money, private records) (19% of 21 others)
What it shares with most of the community
- Is it actively maintained? active (81% of 21 others)
- How is the main thing licensed? permissive open source (MIT/Apache/BSD) (67% of 21 others)
- How is it mainly sustained? company with a paid product, tier, or ads (50% of 20 others)
- Can it run entirely on your own device or infrastructure, without the maker's servers? yes (76% of 21 others)
- Do you need an account to use it? no account (67% of 21 others)
- Who is it for? developers (90% of 21 others)
- What mainly decides whether an action is allowed? rules, policy, or boundaries written in advance (57% of 21 others)
- Which agents does it work with? any agent or process (not limited to a named list) (71% of 21 others)
- In the default setup, where does the agent's work actually execute? directly on the host machine, as usual (52% of 21 others)
- Does it control the agent's outbound network access? no (56% of 16 others)
- Is enforcement kept out of the agent's reach? yes, enforced in code or infrastructure the agent cannot change (95% of 21 others)
Not documented
The public sources we read don't say:
- If the guard itself breaks, is missing, or cannot decide, what happens by default?
- Does it keep a record of agent actions?
Nearest neighbors
- Conduct 80% of 15 shared answers match
- Vultrino 80% of 15 shared answers match
- cMCP (AgenTrust) 79% of 14 shared answers match
Every answer
| Question | Answer | Source |
|---|---|---|
| Is it actively maintained? | active | source 2026-10-25 |
| How is the main thing licensed? | permissive open source (MIT/Apache/BSD) MIT | source 2026-10-25 |
| How is it mainly sustained? | company with a paid product, tier, or ads From Archestra, which sells an enterprise MCP platform. | source 2026-10-25 |
| Can it run entirely on your own device or infrastructure, without the maker's servers? | yes In-process or sidecar; no network calls. | source 2026-10-25 |
| Do you need an account to use it? | no account MIT library run in-process or as a sidecar; no network calls, no account. | source 2026-10-26 |
| Who is it for? | developers | source 2026-10-25 |
| Which shared standard or format does it mainly build on? | none of these (its own format or interface) Own policy algebra with declarative TOML config; plugs into several agents rather than building on one shared standard. | source 2026-10-26 |
| Where does it mainly step in? | at the tool-call, MCP, or API layer (proxy or gateway) | source 2026-10-25 |
| What mainly decides whether an action is allowed? | rules, policy, or boundaries written in advance Declarative TOML; decisions derived algebraically from labels; authorities (human or API) can approve one action. | source 2026-10-25 |
| If the guard itself breaks, is missing, or cannot decide, what happens by default? | Not documented Docs say a blocked action stays blocked if no remedy succeeds; engine-failure behaviour not stated. | source 2026-10-25 |
| Which agents does it work with? | any agent or process (not limited to a named list) Claude Code, Pi, OpenCode, kAgent and others via one integration point. | source 2026-10-25 |
| In the default setup, where does the agent's work actually execute? | directly on the host machine, as usual | source 2026-10-25 |
| What is the main thing it protects? | stands apart outside systems and data (APIs, databases, money, private records) Data exfiltration across tools. | source 2026-10-25 |
| Does it keep a record of agent actions? | Not documented | source 2026-10-25 |
| Does it control the agent's outbound network access? | no Controls data flow to tools, not raw network egress. | source 2026-10-25 |
| What is it mainly for? | letting agents run with fewer approvals, safely 'Deterministic guardrails that don't break agents'; benchmarks task completion. | source 2026-10-25 |
| Is enforcement kept out of the agent's reach? | yes, enforced in code or infrastructure the agent cannot change 'Runs outside the agent's prompt and execution loop.' | source 2026-10-25 |
Sources
This page was derived from:
- GitHub · github.com/archestra-ai/OpenAPPA · read 2026-10-25
- Web page · openappa.com/ · read 2026-10-25
- Web page · www.openappa.com/ · read 2026-10-25
- Web page · www.openappa.com/how-it-works · read 2026-10-25
Are you a maintainer? Claiming and correcting projects is coming soon.